Ridge function explained

In mathematics, a ridge function is any function

f:\Rd\R

that can be written as the composition of a univariate function with an affine transformation, that is:

f(\boldsymbol{x})=g(\boldsymbol{x}\boldsymbol{a})

for some

g:\R\R

and

\boldsymbol{a}\in\Rd

.Coinage of the term 'ridge function' is often attributed to B.F. Logan and L.A. Shepp.[1]

Relevance

A ridge function is not susceptible to the curse of dimensionality, making it an instrumental tool in various estimation problems. This is a direct result of the fact that ridge functions are constant in

d-1

directions:Let

a1,...,ad-1

be

d-1

independent vectors that are orthogonal to

a

, such that these vectors span

d-1

dimensions.Then

f\left(\boldsymbol{x}+

d-1
\sum
k=1

ck\boldsymbol{a}k\right)=g\left(\boldsymbol{x}\boldsymbol{a}+

d-1
\sum
k=1

ck\boldsymbol{a}k\boldsymbol{a}\right)=g\left(\boldsymbol{x}\boldsymbol{a}+

d-1
\sum
k=1

ck0\right)=g(\boldsymbol{x}\boldsymbol{a})=f(\boldsymbol{x})

for all

ci\in\R,1\lei<d

.In other words, any shift of

\boldsymbol{x}

in a direction perpendicular to

\boldsymbol{a}

does not change the value of

f

.

Ridge functions play an essential role in amongst others projection pursuit, generalized linear models, and as activation functions in neural networks. For a survey on ridge functions, see.[2] For books on ridge functions, see.[3] [4]

Notes and References

  1. Logan . B.F. . Shepp . L.A. . Optimal reconstruction of a function from its projections . Duke Mathematical Journal . 1975 . 42 . 4 . 645–659 . 10.1215/S0012-7094-75-04256-8.
  2. Konyagin . S.V. . Kuleshov . A.A. . Maiorov . V.E. . Some Problems in the Theory of Ridge Functions . Proc. Steklov Inst. Math. . 2018 . 301 . 144–169 . 10.1134/S0081543818040120. 126211876 .
  3. Book: Pinkus. Allan. August 2015. Ridge functions. Cambridge . Cambridge Tracts in Mathematics 205. Cambridge University Press. 215 pp. . 9781316408124 .
  4. Book: Ismailov. Vugar. December 2021. Ridge functions and applications in neural networks. Providence, RI . Mathematical Surveys and Monographs 263. American Mathematical Society. 186 pp. . 978-1-4704-6765-4.